joint training

6 papers

• AnaCP: Toward Upper-Bound Continual Learning via Analytic Contrastive Projection
• FlexOLMo: Open Language Models for Flexible Data Use
• Is the acquisition worth the cost? Surrogate losses for Consistent Two-stage Classifiers
• Learning to Specialize: Joint Gating-Expert Training for Adaptive MoEs in Decentralized Settings
• Rectified Point Flow: Generic Point Cloud Pose Estimation
• Toward Efficient Inference Attacks: Shadow Model Sharing via Mixture-of-Experts